VGG16和集成模型（LeNet，CNN，Net均匀池化）比较 -云博客

VGG16和集成模型（LeNet，CNN，Net均匀池化）比较

# 前端 2024-05-05 06:51 0 25 来源：云博客

 1 #导入需要的模块 2 import torch 3 import torch.nn as nn 4 import torch.optim as optim 5 import torch.nn.functional as F 6 import torch.backends.cudnn as cudnn 7 import numpy as np 8 import torchvision 9 import torchvision.transforms as transforms10 from torch.utils.data import DataLoader11 from collections import Counter12 13 #定义一些超参数 14 BATCHSIZE=10015 DOWNLOAD_MNIST=False16 EPOCHES=2017 LR=0.001

 1 #定义相关模型结构，这三个网络结构比较接近 2 class CNNNet(nn.Module): 3 def __init__(self): 4 super(CNNNet,self).__init__() 5 self.conv1 = nn.Conv2d(in_channels=3,out_channels=16,kernel_size=5,stride=1) 6 self.pool1 = nn.MaxPool2d(kernel_size=2,stride=2) 7 self.conv2 = nn.Conv2d(in_channels=16,out_channels=36,kernel_size=3,stride=1) 8 self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2) 9 self.fc1 = nn.Linear(1296,128)10 self.fc2 = nn.Linear(128,10) 11 12 def forward(self,x):13 x=self.pool1(F.relu(self.conv1(x)))14 x=self.pool2(F.relu(self.conv2(x)))15 #print(x.shape)16 x=x.view(-1,36*6*6)17 x=F.relu(self.fc2(F.relu(self.fc1(x))))18 return x19 20 class Net(nn.Module):21 def __init__(self):22 super(Net, self).__init__()23 self.conv1 = nn.Conv2d(3, 16, 5)24 self.pool1 = nn.MaxPool2d(2, 2)25 self.conv2 = nn.Conv2d(16, 36, 5)26 #self.fc1 = nn.Linear(16 * 5 * 5, 120)27 self.pool2 = nn.MaxPool2d(2, 2)28 self.aap=nn.AdaptiveAvgPool2d(1)29 #self.fc2 = nn.Linear(120, 84)30 self.fc3 = nn.Linear(36, 10)31 32 def forward(self, x):33 x = self.pool1(F.relu(self.conv1(x)))34 x = self.pool2(F.relu(self.conv2(x)))35 #print(x.shape)36 #x = x.view(-1, 16 * 5 * 5)37 x = self.aap(x)38 #print(x.shape)39 #x = F.relu(self.fc2(x))40 x = x.view(x.shape[0], -1)41 #print(x.shape)42 x = self.fc3(x)43 return x44 45 class LeNet(nn.Module):46 def __init__(self):47 super(LeNet, self).__init__()48 self.conv1 = nn.Conv2d(3, 6, 5)49 self.conv2 = nn.Conv2d(6, 16, 5)50 self.fc1 = nn.Linear(16*5*5, 120)51 self.fc2 = nn.Linear(120, 84)52 self.fc3 = nn.Linear(84, 10)53 54 def forward(self, x):55 out = F.relu(self.conv1(x))56 out = F.max_pool2d(out, 2)57 out = F.relu(self.conv2(out))58 out = F.max_pool2d(out, 2)59 out = out.view(out.size(0), -1)60 out = F.relu(self.fc1(out))61 out = F.relu(self.fc2(out))62 out = self.fc3(out)63 return out

 1 cfg = { 2 ‘VGG16‘: [64, 64, ‘M‘, 128, 128, ‘M‘, 256, 256, 256, ‘M‘, 512, 512, 512, ‘M‘, 512, 512, 512, ‘M‘], 3 ‘VGG19‘: [64, 64, ‘M‘, 128, 128, ‘M‘, 256, 256, 256, 256, ‘M‘, 512, 512, 512, 512, ‘M‘, 512, 512, 512, 512, ‘M‘], 4 } 5  6  7 class VGG(nn.Module): 8 def __init__(self, vgg_name): 9 super(VGG, self).__init__()10 self.features = self._make_layers(cfg[vgg_name])11 self.classifier = nn.Linear(512, 10)12 13 def forward(self, x):14 out = self.features(x)15 out = out.view(out.size(0), -1)16 out = self.classifier(out)17 return out18 19 def _make_layers(self, cfg):20 layers = []21 in_channels = 322 for x in cfg:23 if x == ‘M‘:24 layers += [nn.MaxPool2d(kernel_size=2, stride=2)]25 else:26 layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),27  nn.BatchNorm2d(x),28 nn.ReLU(inplace=True)]29 in_channels = x30 layers += [nn.AvgPool2d(kernel_size=1, stride=1)]31 return nn.Sequential(*layers)

 1 device = torch.device(‘cuda‘ if torch.cuda.is_available() else ‘cpu‘) 2  3  4 # Data 5 print(‘==> Preparing data..‘) 6 transform_train = transforms.Compose([ 7 transforms.RandomCrop(32, padding=4), 8  transforms.RandomHorizontalFlip(), 9  transforms.ToTensor(),10 transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),11 ])12 13 transform_test = transforms.Compose([14  transforms.ToTensor(),15 transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),16 ])17 18 trainset = torchvision.datasets.CIFAR10(root=r‘D:\JupyterNotebook\PyTorch深度学习代码\PyTorch深度学习代码及数据\pytorch-04\data‘, train=True, download=False, transform=transform_train)19 trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=2)20 21 testset = torchvision.datasets.CIFAR10(root=r‘D:\JupyterNotebook\PyTorch深度学习代码\PyTorch深度学习代码及数据\pytorch-04\data‘, train=False, download=False, transform=transform_test)22 testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)23 24 classes = (‘plane‘, ‘car‘, ‘bird‘, ‘cat‘, ‘deer‘, ‘dog‘, ‘frog‘, ‘horse‘, ‘ship‘, ‘truck‘)25 26 # Model27 print(‘==> Building model..‘)28 net1 = CNNNet()29 net2=Net()30 net3=LeNet()31 net4 = VGG(‘VGG16‘)

#把3个网络模型放在一个列表里mlps=[net1.to(device),net2.to(device),net3.to(device)]optimizer=torch.optim.Adam([{"params":mlp.parameters()} for mlp in mlps],lr=LR) loss_function=nn.CrossEntropyLoss() for ep in range(EPOCHES): for img,label in trainloader: img,label=img.to(device),label.to(device) optimizer.zero_grad()#10个网络清除梯度 for mlp in mlps: mlp.train() out=mlp(img) loss=loss_function(out,label) loss.backward()#网络们获得梯度 optimizer.step() pre=[] vote_correct=0 mlps_correct=[0 for i in range(len(mlps))] for img,label in testloader: img,label=img.to(device),label.to(device) for i, mlp in enumerate( mlps): mlp.eval() out=mlp(img) _,prediction=torch.max(out,1) #按行取最大值 pre_num=prediction.cpu().numpy() mlps_correct[i]+=(pre_num==label.cpu().numpy()).sum() pre.append(pre_num) arr=np.array(pre) pre.clear() result=[Counter(arr[:,i]).most_common(1)[0][0] for i in range(BATCHSIZE)] vote_correct+=(result == label.cpu().numpy()).sum() print("epoch:" + str(ep)+"集成模型的正确率"+str(vote_correct/len(testloader))) for idx, coreect in enumerate( mlps_correct): print("模型"+str(idx)+"的正确率为："+str(coreect/len(testloader)))

epoch:0集成模型的正确率48.14模型0的正确率为：50.01模型1的正确率为：38.74模型2的正确率为：44.7epoch:1集成模型的正确率54.28模型0的正确率为：55.36模型1的正确率为：43.8模型2的正确率为：49.0epoch:2集成模型的正确率58.89模型0的正确率为：60.68模型1的正确率为：48.3模型2的正确率为：52.31epoch:3集成模型的正确率60.43模型0的正确率为：61.96模型1的正确率为：49.04模型2的正确率为：54.25epoch:4集成模型的正确率62.24模型0的正确率为：63.52模型1的正确率为：51.0模型2的正确率为：54.64epoch:5集成模型的正确率62.62模型0的正确率为：63.41模型1的正确率为：52.57模型2的正确率为：56.15epoch:6集成模型的正确率63.88模型0的正确率为：64.45模型1的正确率为：53.33模型2的正确率为：57.71epoch:7集成模型的正确率64.24模型0的正确率为：65.83模型1的正确率为：52.49模型2的正确率为：56.9epoch:8集成模型的正确率66.51模型0的正确率为：67.42模型1的正确率为：55.8模型2的正确率为：59.62epoch:9集成模型的正确率66.83模型0的正确率为：67.33模型1的正确率为：56.49模型2的正确率为：59.85epoch:10集成模型的正确率67.67模型0的正确率为：67.8模型1的正确率为：56.91模型2的正确率为：61.75epoch:11集成模型的正确率67.96模型0的正确率为：68.84模型1的正确率为：56.77模型2的正确率为：61.41epoch:12集成模型的正确率68.75模型0的正确率为：68.42模型1的正确率为：58.25模型2的正确率为：62.13epoch:13集成模型的正确率68.13模型0的正确率为：67.91模型1的正确率为：58.76模型2的正确率为：60.91epoch:14集成模型的正确率68.91模型0的正确率为：68.83模型1的正确率为：58.62模型2的正确率为：62.8epoch:15集成模型的正确率69.3模型0的正确率为：69.12模型1的正确率为：60.16模型2的正确率为：63.29epoch:16集成模型的正确率69.15模型0的正确率为：68.66模型1的正确率为：59.63模型2的正确率为：62.86epoch:17集成模型的正确率70.94模型0的正确率为：69.5模型1的正确率为：60.39模型2的正确率为：64.2epoch:18集成模型的正确率70.97模型0的正确率为：69.43模型1的正确率为：60.27模型2的正确率为：64.34epoch:19集成模型的正确率71.33模型0的正确率为：69.99模型1的正确率为：60.71模型2的正确率为：64.81

mlps=[net4.to(device)]optimizer=torch.optim.Adam([{"params":mlp.parameters()} for mlp in mlps],lr=LR) loss_function=nn.CrossEntropyLoss() for ep in range(EPOCHES): for img,label in trainloader: img,label=img.to(device),label.to(device) optimizer.zero_grad()#10个网络清除梯度 for mlp in mlps: mlp.train() out=mlp(img) loss=loss_function(out,label) loss.backward()#网络们获得梯度 optimizer.step() pre=[] vote_correct=0 mlps_correct=[0 for i in range(len(mlps))] for img,label in testloader: img,label=img.to(device),label.to(device) for i, mlp in enumerate( mlps): mlp.eval() out=mlp(img) _,prediction=torch.max(out,1) #按行取最大值 pre_num=prediction.cpu().numpy() mlps_correct[i]+=(pre_num==label.cpu().numpy()).sum() pre.append(pre_num) arr=np.array(pre) pre.clear() result=[Counter(arr[:,i]).most_common(1)[0][0] for i in range(BATCHSIZE)] vote_correct+=(result == label.cpu().numpy()).sum() #print("epoch:" + str(ep)+"集成模型的正确率"+str(vote_correct/len(testloader))) for idx, coreect in enumerate( mlps_correct): print("VGG16模型迭代"+str(ep)+"次的正确率为："+str(coreect/len(testloader)))

VGG16模型迭代0次的正确率为：49.72VGG16模型迭代1次的正确率为：64.76VGG16模型迭代2次的正确率为：72.55VGG16模型迭代3次的正确率为：75.42VGG16模型迭代4次的正确率为：79.24VGG16模型迭代5次的正确率为：79.82VGG16模型迭代6次的正确率为：82.19VGG16模型迭代7次的正确率为：82.14VGG16模型迭代8次的正确率为：84.04VGG16模型迭代9次的正确率为：84.61VGG16模型迭代10次的正确率为：87.26VGG16模型迭代11次的正确率为：85.57VGG16模型迭代12次的正确率为：85.55VGG16模型迭代13次的正确率为：86.79VGG16模型迭代14次的正确率为：88.49VGG16模型迭代15次的正确率为：87.19VGG16模型迭代16次的正确率为：88.86VGG16模型迭代17次的正确率为：88.56VGG16模型迭代18次的正确率为：88.84VGG16模型迭代19次的正确率为：88.19

from tensorboardX import SummaryWriterinput1 = torch.rand(128,3,32,32)with SummaryWriter(log_dir=‘logs‘,comment=‘Net‘) as w: w.add_graph(net4,(input1,))